In this paper, we study object recognition in the embodied setting. More specifically, we study the problem of whether the recognition system will benefit from acquiring another observation of the object under study, or whether it is time to give up, and report the observed object as unknown. We describe the hardware and software of a system that implements recognition and object permanence as two nested perception-action cycles. We have collected three data sets of observation sequences that allow us to perform controlled evaluation of the system behavior. Our recognition system uses a KNN classifier with bag-of-features prototypes. For this classifier, we have designed and compared three different uncertainty measures for target observation. These measures allow the system to (a) decide whether to continue to observe an object or to move on, and to (b) decide whether the observed object is previously seen or novel. The system is able to successfully reject all novel objects as “unknown”, while still recognizing most of the previously seen objects.

The ability to direct visual attention is a fundamental skill for seeing robots. Attention comes in two flavours: the gaze direction (overt attention) and attention to a specific part of the current field of view (covert attention), of which the latter is the focus of the present study. Specifically, we study the effects of attentional masking within pre-trained deep neural networks for the purpose of handling ambiguous scenes containing multiple objects. We investigate several variants of attentional masking on partially pre-trained deep neural networks and evaluate the effects on classification performance and sensitivity to attention mask errors in multi-object scenes. We find that a combined scheme consisting of multi-level masking and blending provides the best trade-off between classification accuracy and insensitivity to masking errors. This proposed approach is denoted multilayer continuous-valued convolutional feature masking (MC-CFM). For reasonably accurate masks it can suppress the influence of distracting objects and reach comparable classification performance to unmasked recognition in cases without distractors.

This paper describes a method for generation of dense stereo ground-truth using a consumer depth sensor such as the Microsoft Kinect. Such ground-truth allows adaptation of stereo algorithms to a specific setting. The method uses a novel residual weighting based on error propagation from image plane measurements to 3D. We use this ground-truth in wide-angle stereo learning by automatically tuning a novel extension of the best-first-propagation (BFP) dense correspondence algorithm. We extend BFP by adding a coarse-to-fine scheme, and a structure measure that limits propagation along linear structures and flat areas. The tuned correspondence algorithm is evaluated in terms of accuracy, robustness, and ability to generalise. Both the tuning cost function, and the evaluation are designed to balance the accuracy-robustness trade-off inherent in patch-based methods such as BFP.

Segmentation is an important preprocessing step in many applications. Compared to colour segmentation, fusion of colour and depth greatly improves the segmentation result. Such a fusion is easy to do by stacking measurements in different value dimensions, but there are better ways. In this paper we perform fusion using the channel representation, and demonstrate how a state-of-the-art segmentation algorithm can be modified to use channel values as inputs. We evaluate segmentation results on data collected using the Microsoft Kinect peripheral for Xbox 360, using the superparamagnetic clustering algorithm. Our experiments show that depth gradients are more useful than depth values for segmentation, and that channel coding both colour and depth gradients makes tuned parameter settings generalise better to novel images.

A single-camera gaze tracker has been created,based on previous implementations by Shih and Liu[5] and Hennessey et al. [3]. The method used is basedon controlled infrared illumination. The implementedsystem has been evaluated on both synthetic and realimage data and found to be capable of estimatinggaze point with an accuracy of approximately 1° visualangle.

Object recognition is a skill we as humans often take for granted. Due to our formidable object learning, recognition and generalisation skills, it is sometimes hard to see the multitude of obstacles that need to be overcome in order to replicate this skill in an artificial system. Object recognition is also one of the classical areas of computer vision, and many ways of approaching the problem have been proposed. Recently, visually capable robots and autonomous vehicles have increased the focus on embodied recognition systems and active visual search. These applications demand that systems can learn and adapt to their surroundings, and arrive at decisions in a reasonable amount of time, while maintaining high object recognition performance. This is especially challenging due to the high dimensionality of image data. In cases where end-to-end learning from pixels to output is needed, mechanisms designed to make inputs tractable are often necessary for less computationally capable embodied systems.Active visual search also means that mechanisms for attention and gaze control are integral to the object recognition procedure. Therefore, the way in which attention mechanisms should be introduced into feature extraction and estimation algorithms must be carefully considered when constructing a recognition system.This thesis describes work done on the components necessary for creating an embodied recognition system, specifically in the areas of decision uncertainty estimation, object segmentation from multiple cues, adaptation of stereo vision to a specific platform and setting, problem-specific feature selection, efficient estimator training and attentional modulation in convolutional neural networks. Contributions include the evaluation of methods and measures for predicting the potential uncertainty reduction that can be obtained from additional views of an object, allowing for adaptive target observations. Also, in order to separate a specific object from other parts of a scene, it is often necessary to combine multiple cues such as colour and depth in order to obtain satisfactory results. Therefore, a method for combining these using channel coding has been evaluated. In order to make use of three-dimensional spatial structure in recognition, a novel stereo vision algorithm extension along with a framework for automatic stereo tuning have also been investigated. Feature selection and efficient discriminant sampling for decision tree-based estimators have also been implemented. Finally, attentional multi-layer modulation of convolutional neural networks for recognition in cluttered scenes has been evaluated. Several of these components have been tested and evaluated on a purpose-built embodied recognition platform known as Eddie the Embodied.